Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 | /*
* builtin-record.c
*
* Builtin record command: Record the profile of a workload
* (or a CPU, or a PID) into the perf.data output file - for
* later analysis via perf report.
*/
#define _FILE_OFFSET_BITS 64
#include "builtin.h"
#include "perf.h"
#include "util/build-id.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/header.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/symbol.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>
#ifndef HAVE_ON_EXIT
#ifndef ATEXIT_MAX
#define ATEXIT_MAX 32
#endif
static int __on_exit_count = 0;
typedef void (*on_exit_func_t) (int, void *);
static on_exit_func_t __on_exit_funcs[ATEXIT_MAX];
static void *__on_exit_args[ATEXIT_MAX];
static int __exitcode = 0;
static void __handle_on_exit_funcs(void);
static int on_exit(on_exit_func_t function, void *arg);
#define exit(x) (exit)(__exitcode = (x))
static int on_exit(on_exit_func_t function, void *arg)
{
if (__on_exit_count == ATEXIT_MAX)
return -ENOMEM;
else if (__on_exit_count == 0)
atexit(__handle_on_exit_funcs);
__on_exit_funcs[__on_exit_count] = function;
__on_exit_args[__on_exit_count++] = arg;
return 0;
}
static void __handle_on_exit_funcs(void)
{
int i;
for (i = 0; i < __on_exit_count; i++)
__on_exit_funcs[i] (__exitcode, __on_exit_args[i]);
}
#endif
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
};
struct perf_record {
struct perf_tool tool;
struct perf_record_opts opts;
u64 bytes_written;
const char *output_name;
struct perf_evlist *evlist;
struct perf_session *session;
const char *progname;
int output;
unsigned int page_size;
int realtime_prio;
enum write_mode_t write_mode;
bool no_buildid;
bool no_buildid_cache;
bool force;
bool file_new;
bool append_file;
long samples;
off_t post_processing_offset;
};
static void advance_output(struct perf_record *rec, size_t size)
{
rec->bytes_written += size;
}
static int write_output(struct perf_record *rec, void *buf, size_t size)
{
while (size) {
int ret = write(rec->output, buf, size);
if (ret < 0) {
pr_err("failed to write\n");
return -1;
}
size -= ret;
buf += ret;
rec->bytes_written += ret;
}
return 0;
}
static int process_synthesized_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine __maybe_unused)
{
struct perf_record *rec = container_of(tool, struct perf_record, tool);
if (write_output(rec, event, event->header.size) < 0)
return -1;
return 0;
}
static int perf_record__mmap_read(struct perf_record *rec,
struct perf_mmap *md)
{
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
unsigned char *data = md->base + rec->page_size;
unsigned long size;
void *buf;
int rc = 0;
if (old == head)
return 0;
rec->samples++;
size = head - old;
if ((old & md->mask) + size != (head & md->mask)) {
buf = &data[old & md->mask];
size = md->mask + 1 - (old & md->mask);
old += size;
if (write_output(rec, buf, size) < 0) {
rc = -1;
goto out;
}
}
buf = &data[old & md->mask];
size = head - old;
old += size;
if (write_output(rec, buf, size) < 0) {
rc = -1;
goto out;
}
md->prev = old;
perf_mmap__write_tail(md, old);
out:
return rc;
}
static volatile int done = 0;
static volatile int signr = -1;
static volatile int child_finished = 0;
static void sig_handler(int sig)
{
if (sig == SIGCHLD)
child_finished = 1;
done = 1;
signr = sig;
}
static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
{
struct perf_record *rec = arg;
int status;
if (rec->evlist->workload.pid > 0) {
if (!child_finished)
kill(rec->evlist->workload.pid, SIGTERM);
wait(&status);
if (WIFSIGNALED(status))
psignal(WTERMSIG(status), rec->progname);
}
if (signr == -1 || signr == SIGUSR1)
return;
signal(signr, SIG_DFL);
kill(getpid(), signr);
}
static bool perf_evlist__equal(struct perf_evlist *evlist,
struct perf_evlist *other)
{
struct perf_evsel *pos, *pair;
if (evlist->nr_entries != other->nr_entries)
return false;
pair = perf_evlist__first(other);
list_for_each_entry(pos, &evlist->entries, node) {
if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
return false;
pair = perf_evsel__next(pair);
}
return true;
}
static int perf_record__open(struct perf_record *rec)
{
struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
struct perf_record_opts *opts = &rec->opts;
int rc = 0;
/*
* Set the evsel leader links before we configure attributes,
* since some might depend on this info.
*/
if (opts->group)
perf_evlist__set_leader(evlist);
perf_evlist__config_attrs(evlist, opts);
list_for_each_entry(pos, &evlist->entries, node) {
struct perf_event_attr *attr = &pos->attr;
/*
* Check if parse_single_tracepoint_event has already asked for
* PERF_SAMPLE_TIME.
*
* XXX this is kludgy but short term fix for problems introduced by
* eac23d1c that broke 'perf script' by having different sample_types
* when using multiple tracepoint events when we use a perf binary
* that tries to use sample_id_all on an older kernel.
*
* We need to move counter creation to perf_session, support
* different sample_types, etc.
*/
bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
fallback_missing_features:
if (opts->exclude_guest_missing)
attr->exclude_guest = attr->exclude_host = 0;
retry_sample_id:
attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
try_again:
if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
ui__error_paranoid();
rc = -err;
goto out;
} else if (err == ENODEV && opts->target.cpu_list) {
pr_err("No such device - did you specify"
" an out-of-range profile CPU?\n");
rc = -err;
goto out;
} else if (err == EINVAL) {
if (!opts->exclude_guest_missing &&
(attr->exclude_guest || attr->exclude_host)) {
pr_debug("Old kernel, cannot exclude "
"guest or host samples.\n");
opts->exclude_guest_missing = true;
goto fallback_missing_features;
} else if (!opts->sample_id_all_missing) {
/*
* Old kernel, no attr->sample_id_type_all field
*/
opts->sample_id_all_missing = true;
if (!opts->sample_time && !opts->raw_samples && !time_needed)
attr->sample_type &= ~PERF_SAMPLE_TIME;
goto retry_sample_id;
}
}
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support.
*
* PPC returns ENXIO until 2.6.37 (behavior changed
* with commit b0a873e).
*/
if ((err == ENOENT || err == ENXIO)
&& attr->type == PERF_TYPE_HARDWARE
&& attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
ui__warning("The cycles event is not supported, "
"trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
if (pos->name) {
free(pos->name);
pos->name = NULL;
}
goto try_again;
}
if (err == ENOENT) {
ui__error("The %s event is not supported.\n",
perf_evsel__name(pos));
rc = -err;
goto out;
} else if ((err == EOPNOTSUPP) && (attr->precise_ip)) {
ui__error("\'precise\' request may not be supported. "
"Try removing 'p' modifier\n");
rc = -err;
goto out;
}
printf("\n");
error("sys_perf_event_open() syscall returned with %d "
"(%s) for event %s. /bin/dmesg may provide "
"additional information.\n",
err, strerror(err), perf_evsel__name(pos));
#if defined(__i386__) || defined(__x86_64__)
if (attr->type == PERF_TYPE_HARDWARE &&
err == EOPNOTSUPP) {
pr_err("No hardware sampling interrupt available."
" No APIC? If so then you can boot the kernel"
" with the \"lapic\" boot parameter to"
" force-enable it.\n");
rc = -err;
goto out;
}
#endif
pr_err("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
rc = -err;
goto out;
}
}
if (perf_evlist__apply_filters(evlist)) {
error("failed to set filter with %d (%s)\n", errno,
strerror(errno));
rc = -1;
goto out;
}
if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
"/proc/sys/kernel/perf_event_mlock_kb,\n"
"or try again with a smaller value of -m/--mmap_pages.\n"
"(current value: %d)\n", opts->mmap_pages);
rc = -errno;
} else if (!is_power_of_2(opts->mmap_pages) &&
(opts->mmap_pages != UINT_MAX)) {
pr_err("--mmap_pages/-m value must be a power of two.");
rc = -EINVAL;
} else {
pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
rc = -errno;
}
goto out;
}
if (rec->file_new)
session->evlist = evlist;
else {
if (!perf_evlist__equal(session->evlist, evlist)) {
fprintf(stderr, "incompatible append\n");
rc = -1;
goto out;
}
}
perf_session__set_id_hdr_size(session);
out:
return rc;
}
static int process_buildids(struct perf_record *rec)
{
u64 size = lseek(rec->output, 0, SEEK_CUR);
if (size == 0)
return 0;
rec->session->fd = rec->output;
return __perf_session__process_events(rec->session, rec->post_processing_offset,
size - rec->post_processing_offset,
size, &build_id__mark_dso_hit_ops);
}
static void perf_record__exit(int status, void *arg)
{
struct perf_record *rec = arg;
if (status != 0)
return;
if (!rec->opts.pipe_output) {
rec->session->header.data_size += rec->bytes_written;
if (!rec->no_buildid)
process_buildids(rec);
perf_session__write_header(rec->session, rec->evlist,
rec->output, true);
perf_session__delete(rec->session);
perf_evlist__delete(rec->evlist);
symbol__exit();
}
}
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
int err;
struct perf_tool *tool = data;
if (machine__is_host(machine))
return;
/*
*As for guest kernel when processing subcommand record&report,
*we arrange module mmap prior to guest kernel mmap and trigger
*a preload dso because default guest module symbols are loaded
*from guest kallsyms instead of /lib/modules/XXX/XXX. This
*method is used to avoid symbol missing when the first addr is
*in module instead of in guest kernel.
*/
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
/*
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
* have no _text sometimes.
*/
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_text");
if (err < 0)
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_stext");
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
}
static struct perf_event_header finished_round_event = {
.size = sizeof(struct perf_event_header),
.type = PERF_RECORD_FINISHED_ROUND,
};
static int perf_record__mmap_read_all(struct perf_record *rec)
{
int i;
int rc = 0;
for (i = 0; i < rec->evlist->nr_mmaps; i++) {
if (rec->evlist->mmap[i].base) {
if (perf_record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
rc = -1;
goto out;
}
}
}
if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
rc = write_output(rec, &finished_round_event,
sizeof(finished_round_event));
out:
return rc;
}
static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
{
struct stat st;
int flags;
int err, output, feat;
unsigned long waking = 0;
const bool forks = argc > 0;
struct machine *machine;
struct perf_tool *tool = &rec->tool;
struct perf_record_opts *opts = &rec->opts;
struct perf_evlist *evsel_list = rec->evlist;
const char *output_name = rec->output_name;
struct perf_session *session;
bool disabled = false;
rec->progname = argv[0];
rec->page_size = sysconf(_SC_PAGE_SIZE);
on_exit(perf_record__sig_exit, rec);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
if (!output_name) {
if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
opts->pipe_output = true;
else
rec->output_name = output_name = "perf.data";
}
if (output_name) {
if (!strcmp(output_name, "-"))
opts->pipe_output = true;
else if (!stat(output_name, &st) && st.st_size) {
if (rec->write_mode == WRITE_FORCE) {
char oldname[PATH_MAX];
snprintf(oldname, sizeof(oldname), "%s.old",
output_name);
unlink(oldname);
rename(output_name, oldname);
}
} else if (rec->write_mode == WRITE_APPEND) {
rec->write_mode = WRITE_FORCE;
}
}
flags = O_CREAT|O_RDWR;
if (rec->write_mode == WRITE_APPEND)
rec->file_new = 0;
else
flags |= O_TRUNC;
if (opts->pipe_output)
output = STDOUT_FILENO;
else
output = open(output_name, flags, S_IRUSR | S_IWUSR);
if (output < 0) {
perror("failed to create output file");
return -1;
}
rec->output = output;
session = perf_session__new(output_name, O_WRONLY,
rec->write_mode == WRITE_FORCE, false, NULL);
if (session == NULL) {
pr_err("Not enough memory for reading perf file header\n");
return -1;
}
rec->session = session;
for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
perf_header__set_feat(&session->header, feat);
if (rec->no_buildid)
perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
if (!have_tracepoints(&evsel_list->entries))
perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
if (!rec->opts.branch_stack)
perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
if (!rec->file_new) {
err = perf_session__read_header(session, output);
if (err < 0)
goto out_delete_session;
}
if (forks) {
err = perf_evlist__prepare_workload(evsel_list, opts, argv);
if (err < 0) {
pr_err("Couldn't run the workload!\n");
goto out_delete_session;
}
}
if (perf_record__open(rec) != 0) {
err = -1;
goto out_delete_session;
}
/*
* perf_session__delete(session) will be called at perf_record__exit()
*/
on_exit(perf_record__exit, rec);
if (opts->pipe_output) {
err = perf_header__write_pipe(output);
if (err < 0)
goto out_delete_session;
} else if (rec->file_new) {
err = perf_session__write_header(session, evsel_list,
output, false);
if (err < 0)
goto out_delete_session;
}
if (!rec->no_buildid
&& !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
pr_err("Couldn't generate buildids. "
"Use --no-buildid to profile anyway.\n");
err = -1;
goto out_delete_session;
}
rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
machine = perf_session__find_host_machine(session);
if (!machine) {
pr_err("Couldn't find native kernel information.\n");
err = -1;
goto out_delete_session;
}
if (opts->pipe_output) {
err = perf_event__synthesize_attrs(tool, session,
process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
goto out_delete_session;
}
err = perf_event__synthesize_event_types(tool, process_synthesized_event,
machine);
if (err < 0) {
pr_err("Couldn't synthesize event_types.\n");
goto out_delete_session;
}
if (have_tracepoints(&evsel_list->entries)) {
/*
* FIXME err <= 0 here actually means that
* there were no tracepoints so its not really
* an error, just that we don't need to
* synthesize anything. We really have to
* return this more properly and also
* propagate errors that now are calling die()
*/
err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
goto out_delete_session;
}
advance_output(rec, err);
}
}
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_text");
if (err < 0)
err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
machine, "_stext");
if (err < 0)
pr_err("Couldn't record kernel reference relocation symbol\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/kallsyms permission or run as root.\n");
err = perf_event__synthesize_modules(tool, process_synthesized_event,
machine);
if (err < 0)
pr_err("Couldn't record kernel module information.\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/modules permission or run as root.\n");
if (perf_guest)
perf_session__process_machines(session, tool,
perf_event__synthesize_guest_os);
if (!opts->target.system_wide)
err = perf_event__synthesize_thread_map(tool, evsel_list->threads,
process_synthesized_event,
machine);
else
err = perf_event__synthesize_threads(tool, process_synthesized_event,
machine);
if (err != 0)
goto out_delete_session;
if (rec->realtime_prio) {
struct sched_param param;
param.sched_priority = rec->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, ¶m)) {
pr_err("Could not set realtime priority.\n");
err = -1;
goto out_delete_session;
}
}
/*
* When perf is starting the traced process, all the events
* (apart from group members) have enable_on_exec=1 set,
* so don't spoil it by prematurely enabling them.
*/
if (!perf_target__none(&opts->target))
perf_evlist__enable(evsel_list);
/*
* Let the child rip
*/
if (forks)
perf_evlist__start_workload(evsel_list);
for (;;) {
int hits = rec->samples;
if (perf_record__mmap_read_all(rec) < 0) {
err = -1;
goto out_delete_session;
}
if (hits == rec->samples) {
if (done)
break;
err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
waking++;
}
/*
* When perf is starting the traced process, at the end events
* die with the process and we wait for that. Thus no need to
* disable events in this case.
*/
if (done && !disabled && !perf_target__none(&opts->target)) {
perf_evlist__disable(evsel_list);
disabled = true;
}
}
if (quiet || signr == SIGUSR1)
return 0;
fprintf(stderr, "[ perf record: Woken up %ld times to write data ]\n", waking);
/*
* Approximate RIP event size: 24 bytes.
*/
fprintf(stderr,
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
(double)rec->bytes_written / 1024.0 / 1024.0,
output_name,
rec->bytes_written / 24);
return 0;
out_delete_session:
perf_session__delete(session);
return err;
}
#define BRANCH_OPT(n, m) \
{ .name = n, .mode = (m) }
#define BRANCH_END { .name = NULL }
struct branch_mode {
const char *name;
int mode;
};
static const struct branch_mode branch_modes[] = {
BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
BRANCH_END
};
static int
parse_branch_stack(const struct option *opt, const char *str, int unset)
{
#define ONLY_PLM \
(PERF_SAMPLE_BRANCH_USER |\
PERF_SAMPLE_BRANCH_KERNEL |\
PERF_SAMPLE_BRANCH_HV)
uint64_t *mode = (uint64_t *)opt->value;
const struct branch_mode *br;
char *s, *os = NULL, *p;
int ret = -1;
if (unset)
return 0;
/*
* cannot set it twice, -b + --branch-filter for instance
*/
if (*mode)
return -1;
/* str may be NULL in case no arg is passed to -b */
if (str) {
/* because str is read-only */
s = os = strdup(str);
if (!s)
return -1;
for (;;) {
p = strchr(s, ',');
if (p)
*p = '\0';
for (br = branch_modes; br->name; br++) {
if (!strcasecmp(s, br->name))
break;
}
if (!br->name) {
ui__warning("unknown branch filter %s,"
" check man page\n", s);
goto error;
}
*mode |= br->mode;
if (!p)
break;
s = p + 1;
}
}
ret = 0;
/* default to any branch */
if ((*mode & ~ONLY_PLM) == 0) {
*mode = PERF_SAMPLE_BRANCH_ANY;
}
error:
free(os);
return ret;
}
#ifdef LIBUNWIND_SUPPORT
static int get_stack_size(char *str, unsigned long *_size)
{
char *endptr;
unsigned long size;
unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
size = strtoul(str, &endptr, 0);
do {
if (*endptr)
break;
size = round_up(size, sizeof(u64));
if (!size || size > max_size)
break;
*_size = size;
return 0;
} while (0);
pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
max_size, str);
return -1;
}
#endif /* LIBUNWIND_SUPPORT */
static int
parse_callchain_opt(const struct option *opt __maybe_unused, const char *arg,
int unset)
{
struct perf_record *rec = (struct perf_record *)opt->value;
char *tok, *name, *saveptr = NULL;
char *buf;
int ret = -1;
/* --no-call-graph */
if (unset)
return 0;
/* We specified default option if none is provided. */
BUG_ON(!arg);
/* We need buffer that we know we can write to. */
buf = malloc(strlen(arg) + 1);
if (!buf)
return -ENOMEM;
strcpy(buf, arg);
tok = strtok_r((char *)buf, ",", &saveptr);
name = tok ? : (char *)buf;
do {
/* Framepointer style */
if (!strncmp(name, "fp", sizeof("fp"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
rec->opts.call_graph = CALLCHAIN_FP;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for -g fp\n");
break;
#ifdef LIBUNWIND_SUPPORT
/* Dwarf style */
} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
const unsigned long default_stack_dump_size = 8192;
ret = 0;
rec->opts.call_graph = CALLCHAIN_DWARF;
rec->opts.stack_dump_size = default_stack_dump_size;
tok = strtok_r(NULL, ",", &saveptr);
if (tok) {
unsigned long size = 0;
ret = get_stack_size(tok, &size);
rec->opts.stack_dump_size = size;
}
if (!ret)
pr_debug("callchain: stack dump size %d\n",
rec->opts.stack_dump_size);
#endif /* LIBUNWIND_SUPPORT */
} else {
pr_err("callchain: Unknown -g option "
"value: %s\n", arg);
break;
}
} while (0);
free(buf);
if (!ret)
pr_debug("callchain: type %d\n", rec->opts.call_graph);
return ret;
}
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
NULL
};
/*
* XXX Ideally would be local to cmd_record() and passed to a perf_record__new
* because we need to have access to it in perf_record__exit, that is called
* after cmd_record() exits, but since record_options need to be accessible to
* builtin-script, leave it here.
*
* At least we don't ouch it in all the other functions here directly.
*
* Just say no to tons of global variables, sigh.
*/
static struct perf_record record = {
.opts = {
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000,
.target = {
.uses_mmap = true,
},
},
.write_mode = WRITE_FORCE,
.file_new = true,
};
#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
#ifdef LIBUNWIND_SUPPORT
static const char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
#else
static const char callchain_help[] = CALLCHAIN_HELP "[fp]";
#endif
/*
* XXX Will stay a global variable till we fix builtin-script.c to stop messing
* with it and switch to use the library functions in perf_evlist that came
* from builtin-record.c, i.e. use perf_record_opts,
* perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
* using pipes, etc.
*/
const struct option record_options[] = {
OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK(0, "filter", &record.evlist, "filter",
"event filter", parse_filter),
OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
"record events on existing process id"),
OPT_STRING('t', "tid", &record.opts.target.tid, "tid",
"record events on existing thread id"),
OPT_INTEGER('r', "realtime", &record.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_BOOLEAN('D', "no-delay", &record.opts.no_delay,
"collect data without buffering"),
OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
"collect raw sample records from all opened counters"),
OPT_BOOLEAN('a', "all-cpus", &record.opts.target.system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('A', "append", &record.append_file,
"append to the output file to do incremental profiling"),
OPT_STRING('C', "cpu", &record.opts.target.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_BOOLEAN('f', "force", &record.force,
"overwrite existing data file (deprecated)"),
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
OPT_STRING('o', "output", &record.output_name, "file",
"output file name"),
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
"child tasks do not inherit counters"),
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages,
"number of mmap data pages"),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
callchain_help, &parse_callchain_opt,
"fp"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
OPT_BOOLEAN('d', "data", &record.opts.sample_address,
"Sample addresses"),
OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
"don't sample"),
OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
"do not update the buildid cache"),
OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
"do not collect buildids in perf.data"),
OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
"monitor event in cgroup name only",
parse_cgroups),
OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
"user to profile"),
OPT_CALLBACK_NOOPT('b', "branch-any", &record.opts.branch_stack,
"branch any", "sample any taken branches",
parse_branch_stack),
OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
"branch filter mask", "branch stack filter modes",
parse_branch_stack),
OPT_END()
};
int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
{
int err = -ENOMEM;
struct perf_evsel *pos;
struct perf_evlist *evsel_list;
struct perf_record *rec = &record;
char errbuf[BUFSIZ];
evsel_list = perf_evlist__new(NULL, NULL);
if (evsel_list == NULL)
return -ENOMEM;
rec->evlist = evsel_list;
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && perf_target__none(&rec->opts.target))
usage_with_options(record_usage, record_options);
if (rec->force && rec->append_file) {
ui__error("Can't overwrite and append at the same time."
" You need to choose between -f and -A");
usage_with_options(record_usage, record_options);
} else if (rec->append_file) {
rec->write_mode = WRITE_APPEND;
} else {
rec->write_mode = WRITE_FORCE;
}
if (nr_cgroups && !rec->opts.target.system_wide) {
ui__error("cgroup monitoring only available in"
" system-wide mode\n");
usage_with_options(record_usage, record_options);
}
symbol__init();
if (symbol_conf.kptr_restrict)
pr_warning(
"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
"check /proc/sys/kernel/kptr_restrict.\n\n"
"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
"file is not found in the buildid cache or in the vmlinux path.\n\n"
"Samples in kernel modules won't be resolved at all.\n\n"
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
"even with a suitable vmlinux or kallsyms file.\n\n");
if (rec->no_buildid_cache || rec->no_buildid)
disable_buildid_cache();
if (evsel_list->nr_entries == 0 &&
perf_evlist__add_default(evsel_list) < 0) {
pr_err("Not enough memory for event selector list\n");
goto out_symbol_exit;
}
err = perf_target__validate(&rec->opts.target);
if (err) {
perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
ui__warning("%s", errbuf);
}
err = perf_target__parse_uid(&rec->opts.target);
if (err) {
int saved_errno = errno;
perf_target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
ui__error("%s", errbuf);
err = -saved_errno;
goto out_free_fd;
}
err = -ENOMEM;
if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
usage_with_options(record_usage, record_options);
list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos)))
goto out_free_fd;
}
if (rec->opts.user_interval != ULLONG_MAX)
rec->opts.default_interval = rec->opts.user_interval;
if (rec->opts.user_freq != UINT_MAX)
rec->opts.freq = rec->opts.user_freq;
/*
* User specified count overrides default frequency.
*/
if (rec->opts.default_interval)
rec->opts.freq = 0;
else if (rec->opts.freq) {
rec->opts.default_interval = rec->opts.freq;
} else {
ui__error("frequency and count are zero, aborting\n");
err = -EINVAL;
goto out_free_fd;
}
err = __cmd_record(&record, argc, argv);
out_free_fd:
perf_evlist__delete_maps(evsel_list);
out_symbol_exit:
symbol__exit();
return err;
}
|